Neural Machine Translation (NMT) has shown remarkable progress over the past few years, with production systems now being deployed to end-users. As the field is moving rapidly, it has become unclear which elements of NMT architectures have a significant impact on translation quality. In this work, we present a large-scale analysis of the sensitivity of NMT architectures to common hyperparameters. We report empirical results and variance numbers for several hundred experimental runs, corresponding to over 250,000 GPU hours on a WMT English to German translation task. Our experiments provide practical insights into the relative importance of factors such as embedding size, network depth, RNN cell type, residual connections, attention mechanism, and decoding heuristics. As part of this contribution, we also release an open-source NMT framework in TensorFlow to make it easy for others to reproduce our results and perform their own experiments.
Massive Exploration of Neural Machine Translation Architectures
D. Britz,Anna Goldie,Minh-Thang Luong,Quoc V. Le
Published 2017 in Conference on Empirical Methods in Natural Language Processing
ABSTRACT
PUBLICATION RECORD
- Publication year
2017
- Venue
Conference on Empirical Methods in Natural Language Processing
- Publication date
2017-03-11
- Fields of study
Linguistics, Computer Science
- Identifiers
- External record
- Source metadata
Semantic Scholar
CITATION MAP
EXTRACTION MAP
CLAIMS
- No claims are published for this paper.
CONCEPTS
- No concepts are published for this paper.
REFERENCES
Showing 1-33 of 33 references · Page 1 of 1